Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-19 00:01:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

fixed generic image parser

Browse Source 
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7005 6c8d7289-2bf4-0310-a012-ef5d649a1542
This commit is contained in:
orbiter 2010-07-27 07:13:15 +00:00
parent e1015ead2c
commit 989948e1a9
1 changed files with 66 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
source/net/yacy/document/parser/images/genericImageParser.java
View File

@ -27,6 +27,7 @@
package net.yacy.document.parser.images;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.EOFException;
import java.io.File;
import java.io.FileInputStream;
@ -35,10 +36,20 @@ import java.io.IOException;
import java.io.InputStream;import java.net.MalformedURLException;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;
import javax.imageio.ImageIO;
import com.drew.imaging.jpeg.JpegProcessingException;
import com.drew.imaging.jpeg.JpegSegmentReader;
import com.drew.metadata.Directory;
import com.drew.metadata.Metadata;
import com.drew.metadata.MetadataException;
import com.drew.metadata.Tag;
import com.drew.metadata.exif.ExifReader;
import com.drew.metadata.iptc.IptcReader;
import net.yacy.cora.document.MultiProtocolURI;
import net.yacy.document.AbstractParser;
import net.yacy.document.Document;
@ -103,13 +114,65 @@ public class genericImageParser extends AbstractParser implements Parser {
// http://www.drewnoakes.com/drewnoakes.com/code/exif/
// javadoc is at: http://www.drewnoakes.com/drewnoakes.com/code/exif/javadoc/
// a tutorial is at: http://www.drewnoakes.com/drewnoakes.com/code/exif/sampleUsage.html
BufferedImage image = null;
byte[] b;
try {
image = ImageIO.read(sourceStream);
b = FileUtils.read(sourceStream);
} catch (IOException e) {
Log.logException(e);
throw new Parser.Failure(e.getMessage(), location);
}
ii = parseJavaImage(location, image);
ii = parseJavaImage(location, new ByteArrayInputStream(b));
JpegSegmentReader segmentReader;
try {
segmentReader = new JpegSegmentReader(new ByteArrayInputStream(b));
byte[] exifSegment = segmentReader.readSegment(JpegSegmentReader.SEGMENT_APP1);
byte[] iptcSegment = segmentReader.readSegment(JpegSegmentReader.SEGMENT_APPD);
Metadata metadata = new Metadata();
new ExifReader(exifSegment).extract(metadata);
new IptcReader(iptcSegment).extract(metadata);
@SuppressWarnings("unchecked")
Iterator<Directory> directories = metadata.getDirectoryIterator();
HashMap<String, String> props = new HashMap<String, String>();
while (directories.hasNext()) {
Directory directory = directories.next();
@SuppressWarnings("unchecked")
Iterator<Tag> tags = directory.getTagIterator();
while (tags.hasNext()) {
Tag tag = tags.next();
try {
props.put(tag.getTagName(), tag.getDescription());
ii.info.append(tag.getTagName() + ": " + tag.getDescription() + " .\n");
} catch (MetadataException e) {
Log.logException(e);
}
}
title = props.get("Image Description");
if (title == null || title.length() == 0) title = props.get("Headline");
if (title == null || title.length() == 0) title = props.get("Object Name");
author = props.get("Artist");
if (author == null || author.length() == 0) author = props.get("Writer/Editor");
if (author == null || author.length() == 0) author = props.get("By-line");
if (author == null || author.length() == 0) author = props.get("Credit");
if (author == null || author.length() == 0) author = props.get("Make");
keywords = props.get("Keywords");
if (keywords == null || keywords.length() == 0) keywords = props.get("Category");
if (keywords == null || keywords.length() == 0) keywords = props.get("Supplemental Category(s)");
description = props.get("Caption/Abstract");
if (description == null || description.length() == 0) description = props.get("Country/Primary Location");
if (description == null || description.length() == 0) description = props.get("Province/State");
if (description == null || description.length() == 0) description = props.get("Copyright Notice");
}
} catch (JpegProcessingException e) {
Log.logException(e);
// just ignore
}
} else {
ii = parseJavaImage(location, sourceStream);
}